Invasive Computing in HPC with X10

High performance computing with thousands of cores relies on dis-tributed memory due to memory consistency reasons. The resource management on such systems usually relies on static assignment of resources at the start of each application. Such a static scheduling is incapable of starting applications with required resources being used by others since a reduction of resources assigned to applica-tions without stopping them is not possible. This lack of dynamic adaptive scheduling leads to idling resources until the remaining amount of requested resources gets available. Additionally, appli-cations with changing resource requirements lead to idling or less efficiently used resources. The invasive computing paradigm sug-gests dynamic resource scheduling and applications able to dynam-ically adapt to changing resource requirements. As a case study, we developed an invasive resource manager as well as a multigrid with dynamically changing resource demands. Such a multigrid has changing scalability behavior during its ex-ecution and requires data migration upon reallocation due to dis-tributed memory systems. To counteract the additional complexity introduced by the addi-tional interfaces, e. g. for data migration, we use the X10 program-ming language for improved programmability. Our results show improved application throughput and the dynamic adaptivity. In ad-dition, we show our extension for the distributed arrays of X10 to support data migration